
# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask


# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")


nltk.download('all')

[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all

True


# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_movies = pd.read_csv(path + 'ottmovies.csv')
 
df_movies.head()


# profile = ProfileReport(df_movies)
# profile


def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()


data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                 8457
IMDb                 328
Rotten Tomatoes    10437
Directors            357
Cast                 648
Genres               234
Country              303
Language             437
Plotline            4958
Runtime              382
Seasons            16923
dtype: int64
**************************************************
Missing vaules %age wise :

ID                   0.000000
Title                0.000000
Year                 0.000000
Age                 49.973409
IMDb                 1.938191
Rotten Tomatoes     61.673462
Directors            2.109555
Cast                 3.829108
Genres               1.382734
Country              1.790463
Language             2.582284
Plotline            29.297406
Runtime              2.257283
Kind                 0.000000
Seasons            100.000000
Netflix              0.000000
Hulu                 0.000000
Prime Video          0.000000
Disney+              0.000000
Type                 0.000000
dtype: float64
**************************************************
Pictorial Representation :


# ID
# df_movies = df_movies.drop(['ID'], axis = 1)
 
# Age
df_movies.loc[df_movies['Age'].isnull() & df_movies['Disney+'] == 1, "Age"] = '13'
# df_movies.fillna({'Age' : 18}, inplace = True)
df_movies.fillna({'Age' : 'NR'}, inplace = True)
df_movies['Age'].replace({'all': '0'}, inplace = True)
df_movies['Age'].replace({'7+': '7'}, inplace = True)
df_movies['Age'].replace({'13+': '13'}, inplace = True)
df_movies['Age'].replace({'16+': '16'}, inplace = True)
df_movies['Age'].replace({'18+': '18'}, inplace = True)
# df_movies['Age'] = df_movies['Age'].astype(int)
 
# IMDb
# df_movies.fillna({'IMDb' : df_movies['IMDb'].mean()}, inplace = True)
# df_movies.fillna({'IMDb' : df_movies['IMDb'].median()}, inplace = True)
df_movies.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'][df_movies['Rotten Tomatoes'].notnull()].astype(int)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].mean()}, inplace = True)
# df_movies.fillna({'Rotten Tomatoes' : df_movies['Rotten Tomatoes'].median()}, inplace = True)
# df_movies['Rotten Tomatoes'] = df_movies['Rotten Tomatoes'].astype(int)
df_movies.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Directors
# df_movies = df_movies.drop(['Directors'], axis = 1)
df_movies.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_movies.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_movies.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_movies.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_movies.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_movies.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_movies.fillna({'Runtime' : df_movies['Runtime'].mean()}, inplace = True)
# df_movies['Runtime'] = df_movies['Runtime'].astype(int)
df_movies.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_movies.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_movies.fillna({'Type': "NA"}, inplace = True)
# df_movies = df_movies.drop(['Type'], axis = 1)
 
# Seasons
# df_movies.fillna({'Seasons': 1}, inplace = True)
# df_movies.fillna({'Seasons': "NA"}, inplace = True)
df_movies = df_movies.drop(['Seasons'], axis = 1)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
# df_movies.fillna({'Seasons' : df_movies['Seasons'].mean()}, inplace = True)
# df_movies['Seasons'] = df_movies['Seasons'].astype(int)
 
# Service Provider
df_movies['Service Provider'] = df_movies.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_movies.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_movies.dropna(how = 'any', inplace = True)
df_movies.drop_duplicates(inplace = True)


data_investigate(df_movies)

No of Rows :  16923
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation :


df_movies.head()


df_movies.describe()


df_movies.corr()


# df_movies.sort_values('Year', ascending = True)
# df_movies.sort_values('IMDb', ascending = False)


# df_movies.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_ottmovies.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_movies = pd.read_csv(path + 'updated_ottmovies.csv')
 
# udf_movies


# df_netflix_movies = df_movies.loc[(df_movies['Netflix'] > 0)]
# df_hulu_movies = df_movies.loc[(df_movies['Hulu'] > 0)]
# df_prime_video_movies = df_movies.loc[(df_movies['Prime Video'] > 0)]
# df_disney_movies = df_movies.loc[(df_movies['Disney+'] > 0)]


df_netflix_only_movies = df_movies[(df_movies['Netflix'] == 1) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_hulu_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 1) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 0)]
df_prime_video_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 1 ) & (df_movies['Disney+'] == 0)]
df_disney_only_movies = df_movies[(df_movies['Netflix'] == 0) & (df_movies['Hulu'] == 0) & (df_movies['Prime Video'] == 0 ) & (df_movies['Disney+'] == 1)]


df_movies_directors = df_movies.copy()


df_movies_directors.drop(df_movies_directors.loc[df_movies_directors['Directors'] == "NA"].index, inplace = True)
# df_movies_directors = df_movies_directors[df_movies_directors.Director != "NA"]
# df_movies_directors['Director'] = df_movies_directors['Director'].astype(str)


df_movies_count_directors = df_movies_directors.copy()


df_movies_director = df_movies_directors.copy()


# Create directors dict where key=name and value = number of directors
 
directors = {}
 
for i in df_movies_count_directors['Directors'].dropna():
    if i != "NA":
        #print(i,len(i.split(',')))
        directors[i] = len(i.split(','))
    else:
        directors[i] = 0
    
# Add this information to our dataframe as a new column
 
df_movies_count_directors['Number of Directors'] = df_movies_count_directors['Directors'].map(directors).astype(int)


df_movies_mixed_directors = df_movies_count_directors.copy()


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_directors_movies = df_movies_count_directors.loc[df_movies_count_directors['Netflix'] == 1]
hulu_directors_movies = df_movies_count_directors.loc[df_movies_count_directors['Hulu'] == 1]
prime_video_directors_movies = df_movies_count_directors.loc[df_movies_count_directors['Prime Video'] == 1]
disney_directors_movies = df_movies_count_directors.loc[df_movies_count_directors['Disney+'] == 1]


plt.figure(figsize = (10, 10))
corr = df_movies_count_directors.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, alleast annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()

<Figure size 720x720 with 0 Axes>


df_directors_most_movies = df_movies_count_directors.sort_values(by = 'Number of Directors', ascending = False).reset_index()
df_directors_most_movies = df_directors_most_movies.drop(['index'], axis = 1)
# filter = (df_movies_count_directors['Number of Directors'] == (df_movies_count_directors['Number of Directors'].max()))
# df_directors_most_movies = df_movies_count_directors[filter]
 
# mostest_rated_movies = df_movies_count_directors.loc[df_movies_count_directors['Number of Directors'].idxmax()]
 
print('\nMovies with Highest Ever Number of Directors are : \n')
df_directors_most_movies.head(5)

Movies with Highest Ever Number of Directors are :


fig = px.bar(y = df_directors_most_movies['Title'][:15],
             x = df_directors_most_movies['Number of Directors'][:15], 
             color = df_directors_most_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Highest Number of Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_directors_least_movies = df_movies_count_directors.sort_values(by = 'Number of Directors', ascending = True).reset_index()
df_directors_least_movies = df_directors_least_movies.drop(['index'], axis = 1)
# filter = (df_movies_count_directors['Number of Directors'] == (df_movies_count_directors['Number of Directors'].min()))
# df_directors_least_movies = df_movies_count_directors[filter]

print('\nMovies with Lowest Ever Number of Directors are : \n')
df_directors_least_movies.head(5)

Movies with Lowest Ever Number of Directors are :


fig = px.bar(y = df_directors_least_movies['Title'][:15],
             x = df_directors_least_movies['Number of Directors'][:15], 
             color = df_directors_least_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Lowest Number of Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_movies_count_directors['Number of Directors'].unique().shape[0]}' unique Number of Directors s were Given, They were Like this,\n
      
      {df_movies_count_directors.sort_values(by = 'Number of Directors', ascending = False)['Number of Directors'].unique()}\n
 
      The Highest Number of Directors Ever Any Movie Got is '{df_directors_most_movies['Title'][0]}' : '{df_directors_most_movies['Number of Directors'].max()}'\n
 
      The Lowest Number of Directors Ever Any Movie Got is '{df_directors_least_movies['Title'][0]}' : '{df_directors_least_movies['Number of Directors'].min()}'\n
      ''')

      Total '16' unique Number of Directors s were Given, They were Like this,

      
      [28 18 17 13 12 11 10  9  8  7  6  5  4  3  2  1]

 
      The Highest Number of Directors Ever Any Movie Got is 'The Owner' : '28'

 
      The Lowest Number of Directors Ever Any Movie Got is 'Inception' : '1'


netflix_directors_most_movies = df_directors_most_movies.loc[df_directors_most_movies['Netflix']==1].reset_index()
netflix_directors_most_movies = netflix_directors_most_movies.drop(['index'], axis = 1)
 
netflix_directors_least_movies = df_directors_least_movies.loc[df_directors_least_movies['Netflix']==1].reset_index()
netflix_directors_least_movies = netflix_directors_least_movies.drop(['index'], axis = 1)
 
netflix_directors_most_movies.head(5)


fig = px.bar(y = netflix_directors_most_movies['Title'][:15],
             x = netflix_directors_most_movies['Number of Directors'][:15], 
             color = netflix_directors_most_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Highest Number of Directors : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = netflix_directors_least_movies['Title'][:15],
             x = netflix_directors_least_movies['Number of Directors'][:15], 
             color = netflix_directors_least_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Lowest Number of Directors : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


hulu_directors_most_movies = df_directors_most_movies.loc[df_directors_most_movies['Hulu']==1].reset_index()
hulu_directors_most_movies = hulu_directors_most_movies.drop(['index'], axis = 1)
 
hulu_directors_least_movies = df_directors_least_movies.loc[df_directors_least_movies['Hulu']==1].reset_index()
hulu_directors_least_movies = hulu_directors_least_movies.drop(['index'], axis = 1)
 
hulu_directors_most_movies.head(5)


fig = px.bar(y = hulu_directors_most_movies['Title'][:15],
             x = hulu_directors_most_movies['Number of Directors'][:15], 
             color = hulu_directors_most_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Highest Number of Directors : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = hulu_directors_least_movies['Title'][:15],
             x = hulu_directors_least_movies['Number of Directors'][:15], 
             color = hulu_directors_least_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Lowest Number of Directors : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


prime_video_directors_most_movies = df_directors_most_movies.loc[df_directors_most_movies['Prime Video']==1].reset_index()
prime_video_directors_most_movies = prime_video_directors_most_movies.drop(['index'], axis = 1)
 
prime_video_directors_least_movies = df_directors_least_movies.loc[df_directors_least_movies['Prime Video']==1].reset_index()
prime_video_directors_least_movies = prime_video_directors_least_movies.drop(['index'], axis = 1)
 
prime_video_directors_most_movies.head(5)


fig = px.bar(y = prime_video_directors_most_movies['Title'][:15],
             x = prime_video_directors_most_movies['Number of Directors'][:15], 
             color = prime_video_directors_most_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Highest Number of Directors : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = prime_video_directors_least_movies['Title'][:15],
             x = prime_video_directors_least_movies['Number of Directors'][:15], 
             color = prime_video_directors_least_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Lowest Number of Directors : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


disney_directors_most_movies = df_directors_most_movies.loc[df_directors_most_movies['Disney+']==1].reset_index()
disney_directors_most_movies = disney_directors_most_movies.drop(['index'], axis = 1)
 
disney_directors_least_movies = df_directors_least_movies.loc[df_directors_least_movies['Disney+']==1].reset_index()
disney_directors_least_movies = disney_directors_least_movies.drop(['index'], axis = 1)
 
disney_directors_most_movies.head(5)


fig = px.bar(y = disney_directors_most_movies['Title'][:15],
             x = disney_directors_most_movies['Number of Directors'][:15], 
             color = disney_directors_most_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Highest Number of Directors : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = disney_directors_least_movies['Title'][:15],
             x = disney_directors_least_movies['Number of Directors'][:15], 
             color = disney_directors_least_movies['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Directors'},
             title  = 'Movies with Lowest Number of Directors : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      The Movie with Highest Number of Directors Ever Got is '{df_directors_most_movies['Title'][0]}' : '{df_directors_most_movies['Number of Directors'].max()}'\n
      The Movie with Lowest Number of Directors Ever Got is '{df_directors_least_movies['Title'][0]}' : '{df_directors_least_movies['Number of Directors'].min()}'\n
      
      The Movie with Highest Number of Directors on 'Netflix' is '{netflix_directors_most_movies['Title'][0]}' : '{netflix_directors_most_movies['Number of Directors'].max()}'\n
      The Movie with Lowest Number of Directors on 'Netflix' is '{netflix_directors_least_movies['Title'][0]}' : '{netflix_directors_least_movies['Number of Directors'].min()}'\n
      
      The Movie with Highest Number of Directors on 'Hulu' is '{hulu_directors_most_movies['Title'][0]}' : '{hulu_directors_most_movies['Number of Directors'].max()}'\n
      The Movie with Lowest Number of Directors on 'Hulu' is '{hulu_directors_least_movies['Title'][0]}' : '{hulu_directors_least_movies['Number of Directors'].min()}'\n
      
      The Movie with Highest Number of Directors on 'Prime Video' is '{prime_video_directors_most_movies['Title'][0]}' : '{prime_video_directors_most_movies['Number of Directors'].max()}'\n
      The Movie with Lowest Number of Directors on 'Prime Video' is '{prime_video_directors_least_movies['Title'][0]}' : '{prime_video_directors_least_movies['Number of Directors'].min()}'\n
      
      The Movie with Highest Number of Directors on 'Disney+' is '{disney_directors_most_movies['Title'][0]}' : '{disney_directors_most_movies['Number of Directors'].max()}'\n
      The Movie with Lowest Number of Directors on 'Disney+' is '{disney_directors_least_movies['Title'][0]}' : '{disney_directors_least_movies['Number of Directors'].min()}'\n 
      ''')

      The Movie with Highest Number of Directors Ever Got is 'The Owner' : '28'

      The Movie with Lowest Number of Directors Ever Got is 'Inception' : '1'

      
      The Movie with Highest Number of Directors on 'Netflix' is 'Truth or Dare' : '13'

      The Movie with Lowest Number of Directors on 'Netflix' is 'Inception' : '1'

      
      The Movie with Highest Number of Directors on 'Hulu' is 'Wakko's Wish' : '8'

      The Movie with Lowest Number of Directors on 'Hulu' is 'Home Free' : '1'

      
      The Movie with Highest Number of Directors on 'Prime Video' is 'The Owner' : '28'

      The Movie with Lowest Number of Directors on 'Prime Video' is 'Secret Mission' : '1'

      
      The Movie with Highest Number of Directors on 'Disney+' is 'Fantasia' : '12'

      The Movie with Lowest Number of Directors on 'Disney+' is 'The Swap' : '1'


print(f'''
      Accross All Platforms the Average Number of Directors is '{round(df_movies_count_directors['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Netflix' is '{round(netflix_directors_movies['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Hulu' is '{round(hulu_directors_movies['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Prime Video' is '{round(prime_video_directors_movies['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Disney+' is '{round(disney_directors_movies['Number of Directors'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Number of Directors is '1.14'

      The Average Number of Directors on 'Netflix' is '1.15'

      The Average Number of Directors on 'Hulu' is '1.12'

      The Average Number of Directors on 'Prime Video' is '1.13'

      The Average Number of Directors on 'Disney+' is '1.34'


print(f'''
      Accross All Platforms Total Count of Director is '{df_movies_count_directors['Number of Directors'].max()}'\n
      Total Count of Director on 'Netflix' is '{netflix_directors_movies['Number of Directors'].max()}'\n
      Total Count of Director on 'Hulu' is '{hulu_directors_movies['Number of Directors'].max()}'\n
      Total Count of Director on 'Prime Video' is '{prime_video_directors_movies['Number of Directors'].max()}'\n
      Total Count of Director on 'Disney+' is '{disney_directors_movies['Number of Directors'].max()}'\n 
      ''')

      Accross All Platforms Total Count of Director is '28'

      Total Count of Director on 'Netflix' is '13'

      Total Count of Director on 'Hulu' is '8'

      Total Count of Director on 'Prime Video' is '28'

      Total Count of Director on 'Disney+' is '12'


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_movies_count_directors['Number of Directors'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_movies_count_directors['Number of Directors'], ax = ax[1])
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Number of Directors s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_directors_movies['Number of Directors'], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_directors_movies['Number of Directors'], color = 'red', legend = True, kde = True)
sns.histplot(hulu_directors_movies['Number of Directors'], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_directors_movies['Number of Directors'], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


df_lan = df_movies_director['Directors'].str.split(',').apply(pd.Series).stack()
del df_movies_director['Directors']
df_lan.index = df_lan.index.droplevel(-1)
df_lan.name = 'Director'
df_movies_director = df_movies_director.join(df_lan)
df_movies_director.drop_duplicates(inplace = True)


df_movies_director.head(5)


director_count = df_movies_director.groupby('Director')['Title'].count()
director_movies = df_movies_director.groupby('Director')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
director_data_movies = pd.concat([director_count, director_movies], axis = 1).reset_index().rename(columns = {'Title' : 'Movies Count'})
director_data_movies = director_data_movies.sort_values(by = 'Movies Count', ascending = False)


# Director with Movies Counts - All Platforms Combined
director_data_movies.sort_values(by = 'Movies Count', ascending = False)[:10]


fig = px.bar(x = director_data_movies['Director'][:50],
             y = director_data_movies['Movies Count'][:50], 
             color = director_data_movies['Movies Count'][:50],
             color_continuous_scale = 'Teal_r', 
             labels = { 'x' : 'Director', 'y' : 'Movies Count'},
             title  = 'Major Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_director_high_movies = director_data_movies.sort_values(by = 'Movies Count', ascending = False).reset_index()
df_director_high_movies = df_director_high_movies.drop(['index'], axis = 1)
# filter = (director_data_movies['Movies Count'] == (director_data_movies['Movies Count'].max()))
# df_director_high_movies = director_data_movies[filter]
 
# highest_rated_movies = director_data_movies.loc[director_data_movies['Movies Count'].idxmax()]
 
print('\nDirector with Highest Ever Movies Count are : All Platforms Combined\n')
df_director_high_movies.head(5)

Director with Highest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_director_high_movies['Director'][:15],
             x = df_director_high_movies['Movies Count'][:15], 
             color = df_director_high_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Highest Movies : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_director_low_movies = director_data_movies.sort_values(by = 'Movies Count', ascending = True).reset_index()
df_director_low_movies = df_director_low_movies.drop(['index'], axis = 1)
# filter = (director_data_movies['Movies Count'] == (director_data_movies['Movies Count'].min()))
# df_director_low_movies = director_data_movies[filter]

print('\nDirector with Lowest Ever Movies Count are : All Platforms Combined\n')
df_director_low_movies.head(5)

Director with Lowest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_director_low_movies['Director'][:15],
             x = df_director_low_movies['Movies Count'][:15], 
             color = df_director_low_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Lowest Movies Count : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{director_data_movies['Director'].unique().shape[0]}' unique Director Count s were Given, They were Like this,\n
      
      {director_data_movies.sort_values(by = 'Movies Count', ascending = False)['Director'].unique()[:5]}\n
 
      The Highest Ever Movies Count Ever Any Movie Got is '{df_director_high_movies['Director'][0]}' : '{df_director_high_movies['Movies Count'].max()}'\n
 
      The Lowest Ever Movies Count Ever Any Movie Got is '{df_director_low_movies['Director'][0]}' : '{df_director_low_movies['Movies Count'].min()}'\n
      ''')

      Total '12760' unique Director Count s were Given, They were Like this,

      
      ['Jay Chapman' 'Joseph Kane' 'Cheh Chang' 'Sam Newfield' 'Jim Wynorski']

 
      The Highest Ever Movies Count Ever Any Movie Got is 'Jay Chapman' : '36'

 
      The Lowest Ever Movies Count Ever Any Movie Got is 'Peter Ettedgui' : '1'


fig = px.pie(director_data_movies[:10], names = 'Director', values = 'Movies Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'Movies Count based on Director')
fig.show()


# netflix_director_movies = director_data_movies[director_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_director_movies = netflix_director_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
netflix_director_high_movies = df_director_high_movies.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_director_high_movies = netflix_director_high_movies.drop(['index'], axis = 1)
 
netflix_director_low_movies = df_director_high_movies.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_director_low_movies = netflix_director_low_movies.drop(['index'], axis = 1)
 
netflix_director_high_movies.head(5)


fig = px.bar(x = netflix_director_high_movies['Director'][:15],
             y = netflix_director_high_movies['Netflix'][:15], 
             color = netflix_director_high_movies['Netflix'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Highest Movies : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# hulu_director_movies = director_data_movies[director_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_director_movies = hulu_director_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
hulu_director_high_movies = df_director_high_movies.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_director_high_movies = hulu_director_high_movies.drop(['index'], axis = 1)
 
hulu_director_low_movies = df_director_high_movies.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_director_low_movies = hulu_director_low_movies.drop(['index'], axis = 1)
 
hulu_director_high_movies.head(5)


fig = px.bar(x = hulu_director_high_movies['Director'][:15],
             y = hulu_director_high_movies['Hulu'][:15], 
             color = hulu_director_high_movies['Hulu'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Highest Movies : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# prime_video_director_movies = director_data_movies[director_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_director_movies = prime_video_director_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)
 
prime_video_director_high_movies = df_director_high_movies.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_director_high_movies = prime_video_director_high_movies.drop(['index'], axis = 1)
 
prime_video_director_low_movies = df_director_high_movies.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_director_low_movies = prime_video_director_low_movies.drop(['index'], axis = 1)
 
prime_video_director_high_movies.head(5)


fig = px.bar(x = prime_video_director_high_movies['Director'][:15],
             y = prime_video_director_high_movies['Prime Video'][:15], 
             color = prime_video_director_high_movies['Prime Video'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Highest Movies : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# disney_director_movies = director_data_movies[director_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_director_movies = disney_director_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)
 
disney_director_high_movies = df_director_high_movies.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_director_high_movies = disney_director_high_movies.drop(['index'], axis = 1)
 
disney_director_low_movies = df_director_high_movies.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_director_low_movies = disney_director_low_movies.drop(['index'], axis = 1)
 
disney_director_high_movies.head(5)


fig = px.bar(x = disney_director_high_movies['Director'][:15],
             y = disney_director_high_movies['Disney+'][:15], 
             color = disney_director_high_movies['Disney+'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'Movies Count'},
             title  = 'Director with Highest Movies : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(director_data_movies['Movies Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(director_data_movies['Movies Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_director_movies = director_data_movies[director_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_director_movies = netflix_director_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

hulu_director_movies = director_data_movies[director_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_director_movies = hulu_director_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

prime_video_director_movies = director_data_movies[director_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_director_movies = prime_video_director_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)

disney_director_movies = director_data_movies[director_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_director_movies = disney_director_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Director Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(disney_director_movies['Disney+'][:50], color = 'darkblue', legend = True, kde = True)  
sns.histplot(prime_video_director_movies['Prime Video'][:50], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_director_movies['Netflix'][:50], color = 'red', legend = True, kde = True)
sns.histplot(hulu_director_movies['Hulu'][:50], color = 'lightgreen', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Disney+', 'Prime Video', 'Netflix', 'Hulu'])
plt.show()


print(f'''
      The Director with Highest Movies Count Ever Got is '{df_director_high_movies['Director'][0]}' : '{df_director_high_movies['Movies Count'].max()}'\n
      The Director with Lowest Movies Count Ever Got is '{df_director_low_movies['Director'][0]}' : '{df_director_low_movies['Movies Count'].min()}'\n
      
      The Director with Highest Movies Count on 'Netflix' is '{netflix_director_high_movies['Director'][0]}' : '{netflix_director_high_movies['Netflix'].max()}'\n
      The Director with Lowest Movies Count on 'Netflix' is '{netflix_director_low_movies['Director'][0]}' : '{netflix_director_low_movies['Netflix'].min()}'\n
      
      The Director with Highest Movies Count on 'Hulu' is '{hulu_director_high_movies['Director'][0]}' : '{hulu_director_high_movies['Hulu'].max()}'\n
      The Director with Lowest Movies Count on 'Hulu' is '{hulu_director_low_movies['Director'][0]}' : '{hulu_director_low_movies['Hulu'].min()}'\n
      
      The Director with Highest Movies Count on 'Prime Video' is '{prime_video_director_high_movies['Director'][0]}' : '{prime_video_director_high_movies['Prime Video'].max()}'\n
      The Director with Lowest Movies Count on 'Prime Video' is '{prime_video_director_low_movies['Director'][0]}' : '{prime_video_director_low_movies['Prime Video'].min()}'\n
      
      The Director with Highest Movies Count on 'Disney+' is '{disney_director_high_movies['Director'][0]}' : '{disney_director_high_movies['Disney+'].max()}'\n
      The Director with Lowest Movies Count on 'Disney+' is '{disney_director_low_movies['Director'][0]}' : '{disney_director_low_movies['Disney+'].min()}'\n 
      ''')

      The Director with Highest Movies Count Ever Got is 'Jay Chapman' : '36'

      The Director with Lowest Movies Count Ever Got is 'Peter Ettedgui' : '1'

      
      The Director with Highest Movies Count on 'Netflix' is 'Jan Suter' : '21'

      The Director with Lowest Movies Count on 'Netflix' is 'Jeff Rector' : '0'

      
      The Director with Highest Movies Count on 'Hulu' is 'Savage Steve Holland' : '5'

      The Director with Lowest Movies Count on 'Hulu' is 'Jay Chapman' : '0'

      
      The Director with Highest Movies Count on 'Prime Video' is 'Joseph Kane' : '31'

      The Director with Lowest Movies Count on 'Prime Video' is 'Özcan Alper' : '0'

      
      The Director with Highest Movies Count on 'Disney+' is 'Paul Hoen' : '15'

      The Director with Lowest Movies Count on 'Disney+' is 'Jay Chapman' : '0'


# Distribution of movies director in each platform
plt.figure(figsize = (20, 5))
plt.title('Director with Movies Count for All Platforms')
sns.violinplot(x = director_data_movies['Movies Count'][:100], color = 'gold', legend = True, kde = True, shade = False)
plt.show()


# Distribution of Director Movies Count in each platform
f1, ax1 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = netflix_director_movies['Netflix'][:100], color = 'red', ax = ax1[0])
sns.violinplot(x = hulu_director_movies['Hulu'][:100], color = 'lightgreen', ax = ax1[1])
 
f2, ax2 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = prime_video_director_movies['Prime Video'][:100], color = 'lightblue', ax = ax2[0])
sns.violinplot(x = disney_director_movies['Disney+'][:100], color = 'darkblue', ax = ax2[1])
plt.show()


print(f'''
      Accross All Platforms the Average Movies Count of Director is '{round(director_data_movies['Movies Count'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Director on 'Netflix' is '{round(netflix_director_movies['Netflix'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Director on 'Hulu' is '{round(hulu_director_movies['Hulu'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Director on 'Prime Video' is '{round(prime_video_director_movies['Prime Video'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Director on 'Disney+' is '{round(disney_director_movies['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Movies Count of Director is '1.48'

      The Average Movies Count of Director on 'Netflix' is '1.29'

      The Average Movies Count of Director on 'Hulu' is '1.09'

      The Average Movies Count of Director on 'Prime Video' is '1.37'

      The Average Movies Count of Director on 'Disney+' is '1.57'


print(f'''
      Accross All Platforms Total Count of Director is '{director_data_movies['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Netflix' is '{netflix_director_movies['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Hulu' is '{hulu_director_movies['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Prime Video' is '{prime_video_director_movies['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Disney+' is '{disney_director_movies['Director'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Director is '12760'

      Total Count of Director on 'Netflix' is '3174'

      Total Count of Director on 'Hulu' is '1066'

      Total Count of Director on 'Prime Video' is '9909'

      Total Count of Director on 'Disney+' is '473'


plt.figure(figsize = (20, 5))
sns.lineplot(x = director_data_movies['Director'][:10], y = director_data_movies['Netflix'][:10], color = 'red')
sns.lineplot(x = director_data_movies['Director'][:10], y = director_data_movies['Hulu'][:10], color = 'lightgreen')
sns.lineplot(x = director_data_movies['Director'][:10], y = director_data_movies['Prime Video'][:10], color = 'lightblue')
sns.lineplot(x = director_data_movies['Director'][:10], y = director_data_movies['Disney+'][:10], color = 'darkblue')
plt.xlabel('Director', fontsize = 20)
plt.ylabel('Movies Count', fontsize = 20)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_d_ax1 = sns.lineplot(y = director_data_movies['Director'][:10], x = director_data_movies['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_d_ax2 = sns.lineplot(y = director_data_movies['Director'][:10], x = director_data_movies['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_d_ax3 = sns.lineplot(y = director_data_movies['Director'][:10], x = director_data_movies['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_d_ax4 = sns.lineplot(y = director_data_movies['Director'][:10], x = director_data_movies['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(y = netflix_director_movies['Director'][:10], x = netflix_director_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(y = hulu_director_movies['Director'][:10], x = hulu_director_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(y = prime_video_director_movies['Director'][:10], x = prime_video_director_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(y = disney_director_movies['Director'][:10], x = disney_director_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Director  Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_director_movies['Netflix'][:10], color = 'red', legend = True)
sns.kdeplot(hulu_director_movies['Hulu'][:10], color = 'green', legend = True)
sns.kdeplot(prime_video_director_movies['Prime Video'][:10], color = 'lightblue', legend = True)
sns.kdeplot(disney_director_movies['Disney+'][:10], color = 'darkblue', legend = True)                                      
                                      
# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(y = director_data_movies['Director'][:10], x = director_data_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(y = director_data_movies['Director'][:10], x = director_data_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(y = director_data_movies['Director'][:10], x = director_data_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(y = director_data_movies['Director'][:10], x = director_data_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


df_movies_mixed_directors.drop(df_movies_mixed_directors.loc[df_movies_mixed_directors['Directors'] == "NA"].index, inplace = True)
# df_movies_mixed_directors = df_movies_mixed_directors[df_movies_mixed_directors.Director != "NA"]
df_movies_mixed_directors.drop(df_movies_mixed_directors.loc[df_movies_mixed_directors['Number of Directors'] == 1].index, inplace = True)


df_movies_mixed_directors.head(5)


mixed_directors_count = df_movies_mixed_directors.groupby('Directors')['Title'].count()
mixed_directors_movies = df_movies_mixed_directors.groupby('Directors')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
mixed_directors_data_movies = pd.concat([mixed_directors_count, mixed_directors_movies], axis = 1).reset_index().rename(columns = {'Title' : 'Movies Count', 'Directors' : 'Mixed Director'})
mixed_directors_data_movies = mixed_directors_data_movies.sort_values(by = 'Movies Count', ascending = False)


mixed_directors_data_movies.head(5)


# Mixed Director with Movies Counts - All Platforms Combined
mixed_directors_data_movies.sort_values(by = 'Movies Count', ascending = False)[:10]


df_mixed_directors_high_movies = mixed_directors_data_movies.sort_values(by = 'Movies Count', ascending = False).reset_index()
df_mixed_directors_high_movies = df_mixed_directors_high_movies.drop(['index'], axis = 1)
# filter = (mixed_directors_data_movies['Movies Count'] = =  (mixed_directors_data_movies['Movies Count'].max()))
# df_mixed_directors_high_movies = mixed_directors_data_movies[filter]
 
# highest_rated_movies = mixed_directors_data_movies.loc[mixed_directors_data_movies['Movies Count'].idxmax()]
 
print('\nMixed Director with Highest Ever Movies Count are : All Platforms Combined\n')
df_mixed_directors_high_movies.head(5)

Mixed Director with Highest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_mixed_directors_high_movies['Mixed Director'][:15],
             x = df_mixed_directors_high_movies['Movies Count'][:15], 
             color = df_mixed_directors_high_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Mixed Director'},
             title  = 'Movies with Highest Number of Mixed Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_mixed_directors_low_movies = mixed_directors_data_movies.sort_values(by = 'Movies Count', ascending = True).reset_index()
df_mixed_directors_low_movies = df_mixed_directors_low_movies.drop(['index'], axis = 1)
# filter = (mixed_directors_data_movies['Movies Count'] = =  (mixed_directors_data_movies['Movies Count'].min()))
# df_mixed_directors_low_movies = mixed_directors_data_movies[filter]
 
print('\nMixed Director with Lowest Ever Movies Count are : All Platforms Combined\n')
df_mixed_directors_low_movies.head(5)

Mixed Director with Lowest Ever Movies Count are : All Platforms Combined


fig = px.bar(y = df_mixed_directors_low_movies['Mixed Director'][:15],
             x = df_mixed_directors_low_movies['Movies Count'][:15], 
             color = df_mixed_directors_low_movies['Movies Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Movies', 'x' : 'Number of Mixed Director'},
             title  = 'Movies with Lowest Number of Mixed Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_movies_directors['Directors'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see Movies from Total '{mixed_directors_data_movies['Mixed Director'].unique().shape[0]}' Mixed Director, They were Like this, \n
 
      {mixed_directors_data_movies.sort_values(by = 'Movies Count', ascending = False)['Mixed Director'].head(5).unique()} etc. \n
 
      The Mixed Director with Highest Movies Count have '{mixed_directors_data_movies['Movies Count'].max()}' Movies Available is '{df_mixed_directors_high_movies['Mixed Director'][0]}', &\n
      The Mixed Director with Lowest Movies Count have '{mixed_directors_data_movies['Movies Count'].min()}' Movies Available is '{df_mixed_directors_low_movies['Mixed Director'][0]}'
      ''')

      Total '16566' Titles are available on All Platforms, out of which

      You Can Choose to see Movies from Total '1527' Mixed Director, They were Like this, 

 
      ['Raúl Campos,Jan Suter'
 'Abbas Alibhai Burmawalla,Mastan Alibhai Burmawalla'
 'Ethan Coen,Joel Coen' 'Lana Wachowski,Lilly Wachowski'
 'Elizabeth Banks,Steven Brill,Steve Carr,Rusty Cundieff,James Duffy,Griffin Dunne,Peter Farrelly,Patrik Forsberg,Will Graham,James Gunn,Brett Ratner,Jonathan van Tulleken,Bob Odenkirk'] etc. 

 
      The Mixed Director with Highest Movies Count have '20' Movies Available is 'Raúl Campos,Jan Suter', &

      The Mixed Director with Lowest Movies Count have '1' Movies Available is 'Robin Budd,Donovan Cook'


fig = px.pie(mixed_directors_data_movies[:4], names = 'Mixed Director', values = 'Movies Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'Movies Count based on Mixed Director')
fig.show()


# netflix_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_mixed_directors_movies = netflix_mixed_directors_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
netflix_mixed_directors_high_movies = df_mixed_directors_high_movies.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_directors_high_movies = netflix_mixed_directors_high_movies.drop(['index'], axis = 1)
 
netflix_mixed_directors_low_movies = df_mixed_directors_high_movies.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_mixed_directors_low_movies = netflix_mixed_directors_low_movies.drop(['index'], axis = 1)
 
netflix_mixed_directors_high_movies.head(5)


# hulu_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_mixed_directors_movies = hulu_mixed_directors_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)
 
hulu_mixed_directors_high_movies = df_mixed_directors_high_movies.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_directors_high_movies = hulu_mixed_directors_high_movies.drop(['index'], axis = 1)
 
hulu_mixed_directors_low_movies = df_mixed_directors_high_movies.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_mixed_directors_low_movies = hulu_mixed_directors_low_movies.drop(['index'], axis = 1)
 
hulu_mixed_directors_high_movies.head(5)


# prime_video_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_mixed_directors_movies = prime_video_mixed_directors_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)
 
prime_video_mixed_directors_high_movies = df_mixed_directors_high_movies.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_directors_high_movies = prime_video_mixed_directors_high_movies.drop(['index'], axis = 1)
 
prime_video_mixed_directors_low_movies = df_mixed_directors_high_movies.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_mixed_directors_low_movies = prime_video_mixed_directors_low_movies.drop(['index'], axis = 1)
 
prime_video_mixed_directors_high_movies.head(5)


# disney_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_mixed_directors_movies = disney_mixed_directors_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)
 
disney_mixed_directors_high_movies = df_mixed_directors_high_movies.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_directors_high_movies = disney_mixed_directors_high_movies.drop(['index'], axis = 1)
 
disney_mixed_directors_low_movies = df_mixed_directors_high_movies.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_mixed_directors_low_movies = disney_mixed_directors_low_movies.drop(['index'], axis = 1)
 
disney_mixed_directors_high_movies.head(5)


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(mixed_directors_data_movies['Movies Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(mixed_directors_data_movies['Movies Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the movies present on individual streaming platforms
netflix_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_directors_movies = netflix_mixed_directors_movies.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

hulu_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_directors_movies = hulu_mixed_directors_movies.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'Movies Count'], axis = 1)

prime_video_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_directors_movies = prime_video_mixed_directors_movies.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'Movies Count'], axis = 1)

disney_mixed_directors_movies = mixed_directors_data_movies[mixed_directors_data_movies['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_directors_movies = disney_mixed_directors_movies.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'Movies Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Director Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(prime_video_mixed_directors_movies['Prime Video'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_mixed_directors_movies['Netflix'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_mixed_directors_movies['Hulu'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_mixed_directors_movies['Disney+'][:100], color = 'darkblue', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


print(f'''
      The Mixed Director with Highest Movies Count Ever Got is '{df_mixed_directors_high_movies['Mixed Director'][0]}' : '{df_mixed_directors_high_movies['Movies Count'].max()}'\n
      The Mixed Director with Lowest Movies Count Ever Got is '{df_mixed_directors_low_movies['Mixed Director'][0]}' : '{df_mixed_directors_low_movies['Movies Count'].min()}'\n
      
      The Mixed Director with Highest Movies Count on 'Netflix' is '{netflix_mixed_directors_high_movies['Mixed Director'][0]}' : '{netflix_mixed_directors_high_movies['Netflix'].max()}'\n
      The Mixed Director with Lowest Movies Count on 'Netflix' is '{netflix_mixed_directors_low_movies['Mixed Director'][0]}' : '{netflix_mixed_directors_low_movies['Netflix'].min()}'\n
      
      The Mixed Director with Highest Movies Count on 'Hulu' is '{hulu_mixed_directors_high_movies['Mixed Director'][0]}' : '{hulu_mixed_directors_high_movies['Hulu'].max()}'\n
      The Mixed Director with Lowest Movies Count on 'Hulu' is '{hulu_mixed_directors_low_movies['Mixed Director'][0]}' : '{hulu_mixed_directors_low_movies['Hulu'].min()}'\n
      
      The Mixed Director with Highest Movies Count on 'Prime Video' is '{prime_video_mixed_directors_high_movies['Mixed Director'][0]}' : '{prime_video_mixed_directors_high_movies['Prime Video'].max()}'\n
      The Mixed Director with Lowest Movies Count on 'Prime Video' is '{prime_video_mixed_directors_low_movies['Mixed Director'][0]}' : '{prime_video_mixed_directors_low_movies['Prime Video'].min()}'\n
      
      The Mixed Director with Highest Movies Count on 'Disney+' is '{disney_mixed_directors_high_movies['Mixed Director'][0]}' : '{disney_mixed_directors_high_movies['Disney+'].max()}'\n
      The Mixed Director with Lowest Movies Count on 'Disney+' is '{disney_mixed_directors_low_movies['Mixed Director'][0]}' : '{disney_mixed_directors_low_movies['Disney+'].min()}'\n 
      ''')

      The Mixed Director with Highest Movies Count Ever Got is 'Raúl Campos,Jan Suter' : '20'

      The Mixed Director with Lowest Movies Count Ever Got is 'Robin Budd,Donovan Cook' : '1'

      
      The Mixed Director with Highest Movies Count on 'Netflix' is 'Raúl Campos,Jan Suter' : '20'

      The Mixed Director with Lowest Movies Count on 'Netflix' is 'Jim Kammerud,Brian Smith,Bill Speers' : '0'

      
      The Mixed Director with Highest Movies Count on 'Hulu' is 'Don Argott,Sheena M. Joyce' : '2'

      The Mixed Director with Lowest Movies Count on 'Hulu' is 'Raúl Campos,Jan Suter' : '0'

      
      The Mixed Director with Highest Movies Count on 'Prime Video' is 'Abbas Alibhai Burmawalla,Mastan Alibhai Burmawalla' : '6'

      The Mixed Director with Lowest Movies Count on 'Prime Video' is 'Raúl Campos,Jan Suter' : '0'

      
      The Mixed Director with Highest Movies Count on 'Disney+' is 'Anthony Russo,Joe Russo' : '3'

      The Mixed Director with Lowest Movies Count on 'Disney+' is 'Raúl Campos,Jan Suter' : '0'


print(f'''
      Accross All Platforms the Average Movies Count of Mixed Director is '{round(mixed_directors_data_movies['Movies Count'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Director on 'Netflix' is '{round(netflix_mixed_directors_movies['Netflix'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Director on 'Hulu' is '{round(hulu_mixed_directors_movies['Hulu'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Director on 'Prime Video' is '{round(prime_video_mixed_directors_movies['Prime Video'].mean(), ndigits = 2)}'\n
      The Average Movies Count of Mixed Director on 'Disney+' is '{round(disney_mixed_directors_movies['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Movies Count of Mixed Director is '1.1'

      The Average Movies Count of Mixed Director on 'Netflix' is '1.12'

      The Average Movies Count of Mixed Director on 'Hulu' is '1.01'

      The Average Movies Count of Mixed Director on 'Prime Video' is '1.07'

      The Average Movies Count of Mixed Director on 'Disney+' is '1.1'


print(f'''
      Accross All Platforms Total Count of Mixed Director is '{mixed_directors_data_movies['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Netflix' is '{netflix_mixed_directors_movies['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Hulu' is '{hulu_mixed_directors_movies['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Prime Video' is '{prime_video_mixed_directors_movies['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Disney+' is '{disney_mixed_directors_movies['Mixed Director'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Mixed Director is '1527'

      Total Count of Mixed Director on 'Netflix' is '373'

      Total Count of Mixed Director on 'Hulu' is '93'

      Total Count of Mixed Director on 'Prime Video' is '1047'

      Total Count of Mixed Director on 'Disney+' is '104'


plt.figure(figsize = (20, 5))
sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:5], y = mixed_directors_data_movies['Netflix'][:5], color = 'red')
sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:5], y = mixed_directors_data_movies['Hulu'][:5], color = 'lightgreen')
sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:5], y = mixed_directors_data_movies['Prime Video'][:5], color = 'lightblue')
sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:5], y = mixed_directors_data_movies['Disney+'][:5], color = 'darkblue')
plt.xlabel('Mixed Director', fontsize = 15)
plt.ylabel('Movies Count', fontsize = 15)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_md_ax1 = sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_md_ax2 = sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_md_ax3 = sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_md_ax4 = sns.lineplot(x = mixed_directors_data_movies['Mixed Director'][:10], y = mixed_directors_data_movies['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_md_ax1.title.set_text(labels[0])
h_md_ax2.title.set_text(labels[1])
p_md_ax3.title.set_text(labels[2])
d_md_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Director  Movies Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_mixed_directors_movies['Netflix'][:50], color = 'red', legend = True)
sns.kdeplot(hulu_mixed_directors_movies['Hulu'][:50], color = 'green', legend = True)
sns.kdeplot(prime_video_mixed_directors_movies['Prime Video'][:50], color = 'lightblue', legend = True)
sns.kdeplot(disney_mixed_directors_movies['Disney+'][:50], color = 'darkblue', legend = True)                                      

# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_md_ax1 = sns.barplot(x = netflix_mixed_directors_movies['Mixed Director'][:10], y = netflix_mixed_directors_movies['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_md_ax2 = sns.barplot(x = hulu_mixed_directors_movies['Mixed Director'][:10], y = hulu_mixed_directors_movies['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_md_ax3 = sns.barplot(x = prime_video_mixed_directors_movies['Mixed Director'][:10], y = prime_video_mixed_directors_movies['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_md_ax4 = sns.barplot(x = disney_mixed_directors_movies['Mixed Director'][:10], y = disney_mixed_directors_movies['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_md_ax1.title.set_text(labels[0])
h_md_ax2.title.set_text(labels[1])
p_md_ax3.title.set_text(labels[2])
d_md_ax4.title.set_text(labels[3])
 
plt.show()


fig = go.Figure(go.Funnel(y = mixed_directors_data_movies['Mixed Director'][:10], x = mixed_directors_data_movies['Movies Count'][:10]))
fig.show()

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Seasons	Netflix	Prime Video
0	1	Inception	2010	13+	8.8	87%	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	United States,United Kingdom	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148.0	movie	NaN	1	0
1	2	The Matrix	1999	16+	8.7	88%	Lana Wachowski,Lilly Wachowski	Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo...	Action,Sci-Fi	United States	English	Thomas A. Anderson is a man living two lives. ...	136.0	movie	NaN	1	0
2	3	Avengers: Infinity War	2018	13+	8.4	85%	Anthony Russo,Joe Russo	Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo...	Action,Adventure,Sci-Fi	United States	English	As the Avengers and their allies have continue...	149.0	movie	NaN	1	0
3	4	Back to the Future	1985	7+	8.5	96%	Robert Zemeckis	Michael J. Fox,Christopher Lloyd,Lea Thompson,...	Adventure,Comedy,Sci-Fi	United States	English	Marty McFly, a typical American teenager of th...	116.0	movie	NaN	1	0
4	5	The Good, the Bad and the Ugly	1966	16+	8.8	97%	Sergio Leone	Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ...	Western	Italy,Spain,West Germany,United States	Italian	Blondie (The Good) (Clint Eastwood) is a profe...	161.0	movie	NaN	1	1

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Netflix	Prime Video	Service Provider
0	1	Inception	2010	13	8.8	87	Christopher Nolan	Leonardo DiCaprio,Joseph Gordon-Levitt,Elliot ...	Action,Adventure,Sci-Fi,Thriller	United States,United Kingdom	English,Japanese,French	Dom Cobb is a skilled thief, the absolute best...	148	movie	1	0	Netflix
1	2	The Matrix	1999	16	8.7	88	Lana Wachowski,Lilly Wachowski	Keanu Reeves,Laurence Fishburne,Carrie-Anne Mo...	Action,Sci-Fi	United States	English	Thomas A. Anderson is a man living two lives. ...	136	movie	1	0	Netflix
2	3	Avengers: Infinity War	2018	13	8.4	85	Anthony Russo,Joe Russo	Robert Downey Jr.,Chris Hemsworth,Mark Ruffalo...	Action,Adventure,Sci-Fi	United States	English	As the Avengers and their allies have continue...	149	movie	1	0	Netflix
3	4	Back to the Future	1985	7	8.5	96	Robert Zemeckis	Michael J. Fox,Christopher Lloyd,Lea Thompson,...	Adventure,Comedy,Sci-Fi	United States	English	Marty McFly, a typical American teenager of th...	116	movie	1	0	Netflix
4	5	The Good, the Bad and the Ugly	1966	16	8.8	97	Sergio Leone	Eli Wallach,Clint Eastwood,Lee Van Cleef,Aldo ...	Western	Italy,Spain,West Germany,United States	Italian	Blondie (The Good) (Clint Eastwood) is a profe...	161	movie	1	1	Netflix

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
count	16923.000000	16923.000000	16923.000000	16923.000000	16923.000000	16923.000000	16923.0
mean	8462.000000	2003.211901	0.214915	0.062637	0.727235	0.033150	0.0
std	4885.393638	20.526532	0.410775	0.242315	0.445394	0.179034	0.0
min	1.000000	1901.000000	0.000000	0.000000	0.000000	0.000000	0.0
25%	4231.500000	2001.000000	0.000000	0.000000	0.000000	0.000000	0.0
50%	8462.000000	2012.000000	0.000000	0.000000	1.000000	0.000000	0.0
75%	12692.500000	2016.000000	0.000000	0.000000	1.000000	0.000000	0.0
max	16923.000000	2020.000000	1.000000	1.000000	1.000000	1.000000	0.0

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
ID	1.000000	-0.217816	-0.644470	-0.129926	0.469301	0.263530	NaN
Year	-0.217816	1.000000	0.256151	0.101337	-0.255578	-0.047258	NaN
Netflix	-0.644470	0.256151	1.000000	-0.118032	-0.745141	-0.089649	NaN
Hulu	-0.129926	0.101337	-0.118032	1.000000	-0.284654	-0.039693	NaN
Prime Video	0.469301	-0.255578	-0.745141	-0.284654	1.000000	-0.289008	NaN
Disney+	0.263530	-0.047258	-0.089649	-0.039693	-0.289008	1.000000	NaN
Type	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	ID	Title	Year	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Disney+	Service Provider	Number of Directors
0	15786	Fantasia	1940	7.7	95	James Algar,Samuel Armstrong,Ford Beebe Jr.,No...	Deems Taylor,Leopold Stokowski,The Philadelphi...	Animation,Family,Fantasy,Music,Musical	United States	...	Alice, an unpretentious and individual 19-year...	125	movie	1	Disney+	12
1	15797	Bambi	1942	7.3	90	James Algar,Samuel Armstrong,David Hand,Graham...	Hardie Albright,Stan Alexander,Bobette Audrey,...	Animation,Drama,Family	United States	...	When two pre-teens named Hallie and Annie meet...	70	movie	1	Disney+	9
2	16077	Belle's Magical World	1998	5.3	17	Bob Kline,Cullen Blaine,Dale Case,Daniel de la...	Jeff Bennett,Robby Benson,Paige O'Hara,Jim Cum...	Animation,Comedy,Family,Fantasy,Musical,Romance	United States	...	Robbie, the master's baby, has been mysterious...	92	movie	1	Disney+	8
3	15835	Fantasia 2000	1999	7.2	81	James Algar,Gaëtan Brizzi,Paul Brizzi,Hendel B...	Steve Martin,Itzhak Perlman,Quincy Jones,Bette...	Animation,Comedy,Family,Fantasy,Music	United States	...	Captain Jack Sparrow (Johnny Depp) crosses pat...	75	movie	1	Disney+	8
4	15777	Snow White and the Seven Dwarfs	1937	7.6	98	William Cottrell,David Hand,Wilfred Jackson,La...	Roy Atwell,Stuart Buchanan,Adriana Caselotti,E...	Animation,Family,Fantasy,Musical,Romance	United States	...	NA	83	movie	1	Disney+	6

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Netflix	Prime Video	Service Provider	Number of Directors
0	11086	The Owner	2012	NR	6.9	NA	Xavier Agudo,Ian Bonner,Michael Canzoniero,Fra...	Jorge Mario Agudelo,Chiraz Aich,Christine Altm...	Drama	United States,Germany	...	NA	94	movie	0	1	Prime Video	28
1	12269	Fun Size Horror: Volume One	2015	NR	4.6	NA	Bryan Chojnowski,Lisa J Dooley,Ned Ehrbar,Mali...	Tara Perry,Aidan Flynn,Guy Perry,Nev Scharrel,...	Horror	United States	...	Alienated by her peers as a young girl, Scarle...	86	movie	0	1	Prime Video	18
2	11869	A Taste of Phobia	2018	NR	3.1	NA	Domiziano Cristopharo,Jason Impey,Sunny King,S...	Lianne O'Shea,Kehinde Bankole,Roberta Gemma,Ma...	Horror	United Kingdom	...	Blending drama with the explanations of passio...	90	movie	0	1	Prime Video	17
3	4422	The Proposition	2005	16	4.3	85	Elizabeth Banks,Steven Brill,Steve Carr,Rusty ...	Dennis Quaid,Greg Kinnear,Common,Charlie Saxto...	Comedy	United States	...	Ineffectual, 'has-been' film-maker (Dennis Qua...	94	movie	0	1	Prime Video	13
4	2267	Truth or Dare	2017	16	4.3	NA	Elizabeth Banks,Steven Brill,Steve Carr,Rusty ...	Dennis Quaid,Greg Kinnear,Common,Charlie Saxto...	Comedy	United States	...	Ineffectual, 'has-been' film-maker (Dennis Qua...	94	movie	1	1	Netflix	13

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Plotline	Runtime	Kind	Hulu	Prime Video	Service Provider	Number of Directors
0	4032	Wakko's Wish	1999	0	7.3	NA	Liz Holzman,Rusty Mills,Tom Ruegger,Russell Ca...	Rob Paulsen,Jess Harnell,Tress MacNeille,Mauri...	Animation,Adventure,Comedy,Drama,Family,Fantas...	United States	...	The Warner Brothers (and the Warner Sister) go...	80	movie	1	0	Hulu	8
1	3704	Southbound	2015	16	5.9	81	Roxanne Benjamin,Matt Bettinelli-Olpin,David B...	Chad Villella,Matt Bettinelli-Olpin,Kristina P...	Horror	United States	...	On a desolate stretch of desert highway, weary...	89	movie	1	1	Prime Video	8
2	3912	Tiny Toon Adventures: How I Spent My Vacation	1992	NR	8	NA	Rich Arons,Ken Boyer,Kent Butterworth,Barry Ca...	Charlie Adler,Tress MacNeille,Joe Alaskey,Don ...	Animation,Adventure,Comedy,Family,Fantasy	United States	...	Term-time ends at Acme Looniversity and the Ti...	79	movie	1	0	Hulu	7
3	16501	Victoria's Secret Fashion Show	1999	7	7.6	NA	Hamish Hamilton,Yemisi Brookes,Dee Koppang O'L...	Behati Prinsloo,Adriana Lima,Alessandra Ambros...	Reality-TV	United States	...	Shinichi Kanou is a young secluded Otaku who i...	45	movie	1	0	Hulu	4
4	3531	The Prince of Egypt	1998	7	7.1	80	Brenda Chapman,Steve Hickner,Simon Wells	Val Kilmer,Ralph Fiennes,Michelle Pfeiffer,San...	Animation,Adventure,Drama,Family,Fantasy,Musical	United States,France,United Kingdom	...	This is the extraordinary tale of two brothers...	99	movie	1	0	Hulu	3

	Director	Movies Count	Netflix	Hulu	Prime Video	Disney+
5226	Jay Chapman	36	12	0	29	0
6248	Joseph Kane	31	0	0	31	0
1985	Cheh Chang	29	2	0	28	0
10597	Sam Newfield	23	1	0	22	0
5621	Jim Wynorski	23	0	0	23	0
5107	Jan Suter	21	21	0	0	0
2792	David DeCoteau	21	0	0	21	0
9783	Raúl Campos	21	21	0	0	0
5232	Jay Karas	21	15	1	6	1
12460	William Beaudine	20	0	0	20	0

	Director	Movies Count	Netflix	Hulu	Prime Video
0	Peter Ettedgui	1	0	0	1
1	Dexton Deboree	1	0	1	0
2	Dezsö Magyar	1	0	0	1
3	Dhanush	1	1	0	1
4	Dheer Momaya	1	1	0	0

	Director	Movies Count	Netflix	Hulu	Prime Video	Disney+
0	Jan Suter	21	21	0	0	0
1	Raúl Campos	21	21	0	0	0
2	Marcus Raboy	18	16	0	2	0
3	Jay Karas	21	15	1	6	1
4	Jay Chapman	36	12	0	29	0

	Director	Movies Count	Netflix	Hulu	Prime Video	Disney+
0	Savage Steve Holland	6	2	5	0	1
1	Tyler Perry	6	2	4	4	0
2	Richard Rich	10	2	4	2	2
3	Alan Metter	4	1	3	1	0
4	William Lau	5	2	3	0	0

	Director	Movies Count	Hulu	Prime Video	Disney+
0	Paul Hoen	15	0	0	15
1	James Algar	12	0	0	12
2	Robert Stevenson	14	1	2	11
3	Vincent McEveety	9	0	0	9
4	Kenny Ortega	8	0	0	8

	Mixed Director	Movies Count	Netflix	Hulu	Prime Video
1174	Raúl Campos,Jan Suter	20	20	0	0
11	Abbas Alibhai Burmawalla,Mastan Alibhai Burmaw...	7	2	0	6
467	Ethan Coen,Joel Coen	6	4	1	2
882	Lana Wachowski,Lilly Wachowski	5	4	0	1
455	Elizabeth Banks,Steven Brill,Steve Carr,Rusty ...	5	2	0	4

	Mixed Director	Movies Count	Prime Video	Disney+
0	Robin Budd,Donovan Cook	1	0	1
1	Andrew Stanton,Lee Unkrich	1	0	1
2	Alex Harvey,Tommy Sowards	1	1	0
3	Alex Kleider,Corey Ogilvie	1	1	0
4	Amber Dawn Lee,Rob Brownstein,Jeff Chassler,Ro...	1	1	0

	Mixed Director	Movies Count	Hulu	Prime Video
0	Don Argott,Sheena M. Joyce	2	2	0
1	Jocelyn DeBoer,Dawn Luebbe	1	1	0
2	Stuart Walker,Mitchell Leisen	1	1	1
3	Alexander Lahl,Max Mönch	1	1	0
4	Steve Jones,Todd Jones	1	1	1

	Mixed Director	Movies Count	Netflix	Prime Video
0	Abbas Alibhai Burmawalla,Mastan Alibhai Burmaw...	7	2	6
1	Frank Capra,Anatole Litvak	5	2	5
2	Elizabeth Banks,Steven Brill,Steve Carr,Rusty ...	5	2	4
3	Eduardo Quiroz,Jose Quiroz	4	0	4
4	Fenton Bailey,Randy Barbato	4	0	4

	Mixed Director	Movies Count	Netflix	Prime Video	Disney+
0	Anthony Russo,Joe Russo	5	1	1	3
1	Ron Clements,John Musker	3	1	0	3
2	Robert C. Ramirez,Patrick A. Ventura	2	0	0	2
3	Chris Buck,Jennifer Lee	2	0	0	2
4	Saul Blinkoff,Elliot M. Bour	2	0	0	2